© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 30656
    Prev
    Next
    INDEX
    Explanations

    concepts related to supply management and availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    459
    +0.14
    0.6%
    653
    +0.12
    0.6%
    322
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.14
    0.03
    288
    +0.12
    0.03
    724
    +0.11
    0.03
    Negative Logits
    uate
    -0.80
    ormal
    -0.77
    laughter
    -0.69
    ounty
    -0.67
    achelor
    -0.66
    laus
    -0.66
    ayne
    -0.65
    doms
    -0.65
    ceed
    -0.64
    osaurs
    -0.64
    POSITIVE LOGITS
     chain
    1.22
     Chain
    1.13
     chains
    1.11
     shortages
    0.99
     Crate
    0.95
     Chains
    0.91
     Depot
    0.85
     depot
    0.82
    ãĥ¼ãĥĨãĤ£
    0.81
     glut
    0.79
    Activations Density 0.196%

    No Known Activations